# Counterfactual Reciprocal Recommender Systems for User-to-User Matching

arXiv: https://arxiv.org/abs/2508.01867 · HTML: https://mlsanity.com/paper/2508.01867/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 36 references that are in the map.
- First posted on arXiv 3 Aug 2025.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Recommendations as Treatments: Debiasing Learning and Evaluation](https://mlsanity.com/paper/1602.05352/) (2016)
- [Doubly Robust Policy Evaluation and Optimization](https://mlsanity.com/paper/1503.02834/) (2015)
- [Unbiased Learning-to-Rank with Biased Feedback](https://mlsanity.com/paper/1608.04468/) (2016)
- [Equity of Attention: Amortizing Individual Fairness in Rankings](https://mlsanity.com/paper/1805.01788/) (2018)
- [How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility](https://mlsanity.com/paper/1710.11214/) (2017)
- [User-centered Evaluation of Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2103.06364/) (2021)
- [StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Random](https://mlsanity.com/paper/2205.04701/) (2022)
- [Aspirational pursuit of mates in online dating markets](https://mlsanity.com/paper/1808.04840/) (2018)
- [Correcting the User Feedback-Loop Bias for Recommendation Systems](https://mlsanity.com/paper/2109.06037/) (2021)
- [Revisiting Reciprocal Recommender Systems: Metrics, Formulation, and Method](https://mlsanity.com/paper/2408.09748/) (2024)
- [Fair Reciprocal Recommendation in Matching Markets](https://mlsanity.com/paper/2409.00720/) (2024)
- [Maximizing Nash Social Welfare under Two-Sided Preferences](https://mlsanity.com/paper/2312.09167/) (2023)
- [Parallel and Mini-Batch Stable Matching for Large-Scale Reciprocal Recommender Systems](https://mlsanity.com/paper/2411.19214/) (2024)

## Abstract (arXiv)

Reciprocal recommender systems (RRS) in dating, gaming, and talent platforms require mutual acceptance for a match. Logged data, however, over-represents popular profiles due to past exposure policies, creating feedback loops that skew learning and fairness. We introduce Counterfactual Reciprocal Recommender Systems (CFRR), a causal framework to mitigate this bias. CFRR uses inverse propensity scored, self-normalized objectives. Experiments show CFRR improves NDCG@10 by up to 3.5% (e.g., from 0.459 to 0.475 on DBLP, from 0.299 to 0.307 on Synthetic), increases long-tail user coverage by up to 51% (from 0.504 to 0.763 on Synthetic), and reduces Gini exposure inequality by up to 24% (from 0.708 to 0.535 on Synthetic). CFRR offers a promising approach for more accurate and fair user-to-user matching.